The spatial support required for image restoration varies across degradation types, image regions, and reconstruction stages. However, most existing methods rely on predefined multi-scale hierarchies and aggregate features through fixed fusion or attention, leaving the representation scale itself largely determined by...
Image restoration models are typically trained with a fixed set of capabilities. When new restoration requirements emerge, existing solutions usually train additional models or jointly retrain the original model with both new and historical data. Instead of designing another restoration backbone, we investigate how a t...
This work proposes to adopt fatigue as a proxy of the finite energy limit, inject it into general character animation, and thoroughly investigate how fatigue introduces new characteristics to physics-based character control.
Shengyuan Zhang, Xinpeng Liu, Mu-Chun Niu et al.· 0 citations
Despite recent advances in unified multimodal models for multi-reference image generation, existing benchmarks remain organized around predefined task types (e.g.,"subject composition"), which are ill-suited to this combinatorial setting and lead to fragmented coverage, uncontrolled complexity, and little diagnostic va...
Haoran Wang, Chaofan Ma, Ran Yi et al.· 0 citations
This work proposes Visual In-context Editing, a new paradigm elevating video editing from textual instructions to multi-modal visual guidance encompassing single image, image pair, and video pair, and curates VicEdit-400K, the first large-scale dataset for visual in-context video editing.
Yu-Ji Wang, Teng Hu, Yu-Heng Chen et al.· 0 citations
This work proposes GroupForward, an instance-grouped feed-forward Gaussian splatting model that reconstructs geometry, appearance, instance structure, and semantics from sparse, unposed, and uncalibrated multi-view images and proposes a Referential Scene Reasoning Framework (RSRF) for complex 3D referring segmentation.
Qi-Jian Tian, Zimeng Wu, Xuhong Wang et al.· 0 citations
This work proposes Change and Invariance Motion Editing (CIME), a unified framework that comprehensively decouples change and invariance into spatial pose and temporal rhythm dimensions and introduces the Riemannian Non-uniform Integral Manifold Mapping module.
Shaohui Lin, Zhenwu Shi, Jingyu Gong et al.· 0 citations
This work proposes Cycle-World, a novel framework designed for stable and temporally consistent long-video generation that tackles error drift by enforcing strict temporal reversibility across both the training and inference phases, and demonstrates that forward generative drift can be strictly bottlenecked by a cycle-...
Zihan Su, Teng Hu, Jiangning Zhang et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
